Information for final projects

• Only one submission required per group, submitted to gradescope

• Score will be on the scale of 4-7:

  • 7 means you have exceeded my expectations, everything is perfect
  • 4 means that there are serious conceptual errors or that apparently little effort has been given to organization or presentation
  • 5 and 6 are everything that aren’t 4 or 7. Better than average is 6, less than average is 5

• These are officially due Friday, May 9, but you may submit them by Wednesday, May 15 at 5pm sharp.

• I will have walk-in consulting hours on Sunday, May 11 from 1-3pm in my office or Monday, May 12 from 1pm-5pm

• You may have up to 10 minutes, and you are only permitted one session

Information for Final Exam

Review session led by me on Sunday, May 11 from 3pm-5pm in Noyce 2022

• STA-209-02 Tuesday afternoon, STA-209-05 Tuesday morning
• You will be allowed to choose day of which exam you want (cumulative or exam 3 only)
• Cumulative will replace lowest exam grade unless your cumulative exam is lowest
• 3 hours will be allowed regardless of which exam you choose
• Double-sided notecard is OK

Exam 3 Topics List

Decision Error

• Bonferonni/FWER/Multiple comparisons
• Type I vs Type II error
• What is statistical power?
• Creating table with false positives/negatives

Types of tests and associated variables

• t-test/paired t-test (degrees of freedom)
• Chi-squared goodness of fit/independence
• ANOVA
• Regression

\(\chi^2\) Tests

• Null hypothesis
• Expected values
• Compute statistic
• Use critical value sheet

ANOVA

• Degrees of freedom
• What impacts F statistic
• Within vs between variability
• MSE and MSG
• Use for prediction
• Tukey HSD

Regression

• Interpret and write models
• Categorical (reference and indicators (testing difference))
• Inference for slope parameter
• Correlated predictors
• \(R^2\) and model comparison
• Residuals

Comprehensive Topics List

Exam 1

Statistical framework (parameter vs statistic)

Quantitative vs Categorical variables

What is a distribution?

• What values?
• How frequently?

Tables and Odds

• Conditional statistics (row/column/total)
• Associate plots with tables
• Use quantitative variable as categorical (i.e., enrollment as large or small)
• Odds vs probability (go from one to the other)
• Exposure/non-exposure and event/non-event
• Odds ratios (OR < 1, OR = 1, OR > 1)

Z-scores

• What do the tell us about observations?
• Be able to construct given mean and sd
• Interpret

Exam 2

Sampling Distribution

• Distributional parameters
• Standard error vs standard deviation
• Sampling distribution definition
• Central Limit Theorem conditions
  • When does it apply? When does it not?
  • When is approximation likely correct?
• Normal distribution
• Standard normal distribution

Confidence Intervals

• Critical values and quantiles
• t-distribution
• How does each term impact location and size of CI
• Coverage probability (what does this mean?)

Hypothesis Testing

• What is a t-statistic? Can you write it?
• What is a t-test?
• Null Hypothesis and null distribution (sampling distribution when null is true)

Do not need to know

How to compute p-values directly

Probability (i.e., Bayes and probability rules, though you should still understand tables and conditionals (i.e., given placebo, what is probability of cancer))

Types of study design

Computing SSE or SSG directly

R programming